23 citations · 146 across the 33 of their papers we have counts for
12 papers · 1 filter
Effective Whole-body Pose Estimation with Two-stages Distillation
Zhendong Yang, Ailing Zeng, Chun Yuan +1
Whole-body pose estimation localizes the human body, hand, face, and foot keypoints in an image. This task is challenging due to multi-scale body parts, fine-grained localization f…
DreamDiffusion: Generating High-Quality Images from Brain EEG Signals
Yunpeng Bai, Xintao Wang, Yan-pei Cao +3
This paper introduces DreamDiffusion, a novel method for generating high-quality images directly from brain electroencephalogram (EEG) signals, without the need to translate though…
Towards Effective Collaborative Learning in Long-Tailed Recognition
Zhengzhuo Xu, Zenghao Chai, Chengyin Xu +2
Real-world data usually suffers from severe class imbalance and long-tailed distributions, where minority classes are significantly underrepresented compared to the majority ones.…
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang +3
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing…
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Anyi Rao +3
Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical…
Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
Yuxin Ren, Zihan Zhong, Xingjian Shi +3
It has been commonly observed that a teacher model with superior performance does not necessarily result in a stronger student, highlighting a discrepancy between current teacher t…
HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting
Haoyu Wang, Shaoli Huang, Fang Zhao +2
We present a simple yet effective method for skeleton-free motion retargeting. Previous methods transfer motion between high-resolution meshes, failing to preserve the inherent loc…
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Zhendong Yang, Ailing Zeng, Zhe Li +3
Knowledge Distillation (KD) uses the teacher's prediction logits as soft labels to guide the student, while self-KD does not need a real teacher to require the soft labels. This wo…
HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details
Zenghao Chai, Tianke Zhang, Tianyu He +7
3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image. The facial surface is influenced by the c…
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang +3
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data. However, existing works only s…
Rethink Long-tailed Recognition with Vision Transformers
Zhengzhuo Xu, Shuo Yang, Xingjun Wang +1
In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we r…
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Dachuan Shi, Chaofan Tao, Ying Jin +3
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models,…